Quality of care and economic considerations of active surveillance of men with prostate cancer

68Ga-PSMA-PET/CT in addition to mpMRI in men undergoing biopsy during active surveillance for low- to intermediate-risk prostate cancer: study protocol for a prospective cross-sectional study

Background

In active surveillance there is significant interest in whether imaging modalities such as multiparametric magnetic resonance imaging (mpMRI) or 68Gallium prostate-specific membrane antigen positron emission tomography/computerized tomography (68Ga-PSMA-PET/CT) can improve the detection of progression to clinically significant prostate cancer (csPCa) and thus reduce the frequency of prostate biopsies and associated morbidity. Recent studies have demonstrated the value of mpMRI in active surveillance; however, mpMRI does miss a proportion of disease progression and thus alone cannot replace biopsy. To date, prostate-specific membrane antigen positron emission tomography (PSMA-PET) has shown additive value to mpMRI in its ability to detect prostate cancer (PCa) in the primary diagnostic setting. Our objective is to evaluate the diagnostic utility of PSMA-PET to detect progression to csPCa in active surveillance patients.

Methods

We will perform a prospective, cross-sectional, partially blinded, multicentre clinical trial evaluating the additive value of PSMA-PET with mpMRI against saturation transperineal template prostate biopsy. Two hundred and twenty-five men will be recruited who have newly diagnosed PCa which is suitable for active surveillance. Following enrolment, patients will undergo a PSMA-PET and mpMRI within 3 months of a repeat 12-month confirmatory biopsy. Patients who remain on active surveillance after confirmatory biopsy will then be planned to have a further mpMRI and PSMA-PET prior to a repeat biopsy in 3-4 years. The primary outcome is to assess the ability of PSMA-PET to detect or exclude significant malignancy on repeat biopsy. Secondary outcomes include (I) assess the comparative diagnostic accuracies of mpMRI and PSMA-PET alone [sensitivity/specificity/negative predictive value (NPV)/positive predictive value (PPV)] to detect progression on biopsy based on predefined histologic criteria for progression; (II) comparison of index lesion identification by template biopsies vs. MRI targeted lesions vs. PSMA targeted lesions; (III) evaluation of concordance of lesions identified on final histopathology and each imaging modality (PSMA-PET and/or mpMRI) in the subset of patients proceeding to RP.

Discussion

The results of this trial will define the role of PSMA-PET in active surveillance and potentially reduce the number of biopsies needed to detect progression to csPCa.

Trial Registration

The current trial was registered with the ANZCTR on the 3/2/2022 with the trial ID ACTRN12622000188730, it is accessible at https://www.anzctr.org.au/.

Comparison of orthogonal NLP methods for clinical phenotyping and assessment of bone scan utilization among prostate cancer patients

OBJECTIVE

Clinical care guidelines recommend that newly diagnosed prostate cancer patients at high risk for metastatic spread receive a bone scan prior to treatment and that low risk patients not receive it. The objective was to develop an automated pipeline to interrogate heterogeneous data to evaluate the use of bone scans using a two different Natural Language Processing (NLP) approaches.

MATERIALS AND METHODS

Our cohort was divided into risk groups based on Electronic Health Records (EHR). Information on bone scan utilization was identified in both structured data and free text from clinical notes. Our pipeline annotated sentences with a combination of a rule-based method using the ConText algorithm (a generalization of NegEx) and a Convolutional Neural Network (CNN) method using word2vec to produce word embeddings.

RESULTS

A total of 5500 patients and 369,764 notes were included in the study. A total of 39% of patients were high-risk and 73% of these received a bone scan; of the 18% low risk patients, 10% received one. The accuracy of CNN model outperformed the rule-based model one (F-measure = 0.918 and 0.897 respectively). We demonstrate a combination of both models could maximize precision or recall, based on the study question.

CONCLUSION

Using structured data, we accurately classified patients' cancer risk group, identified bone scan documentation with two NLP methods, and evaluated guideline adherence. Our pipeline can be used to provide concrete feedback to clinicians and guide treatment decisions.